Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 4

UNDERSTANDING

WHAT IS UNDERSTANDING?

To understand something is to transform it from one representation into another, where this second
representation has been chosen to correspond to a set of available actions that could be performed and
where the mapping has been designed so that for each event, an appropriate action will be performed.

If you say to an airline database system "I need to go to New York as soon possible," the system will have
"understood" if it finds the first available plane to New York. If you say the same thing to your best
friend, who knows that your family lives in New York, she will have "understood" she realizes that there
may be a problem in your family and you may need some emotional support. As we talk about
understanding, it is important to keep in mind that the success or failure of an "understanding" program
can rarely be measured in an absolute sense & task to be performed.

Understanding in various aspects:

 For people, understanding applies to inputs from all the senses.


 Computer understanding has applied primarily to images, speech, and typed language.

WHAT MAKES UNDERSTANDING HARD?

There are four major factors that contribute to the difficulty of an understanding problem:
1. The complexity of the target representation into which the matching is being done
2. The type of the mapping: one-one, many-one, one-many, or many-many
3. The level of interaction of the components of the source representation
4. The presence of noise in the input to the understander

Examples to illustrate factors of understanding:


1. Complexity of the Target Representation
Suppose English sentences are being used for communication with a keyword-based data
retrieval system. Then the sentence

I want to read all about the last budget & result.

would need to be translated into a representation such as

(SEARCH KEYWORDS =BUDGET & RESULT)

Extracting that information often requires the use of additional knowledge about the world
described by the sentences.

2. Type of Mapping
Understanding is the process of mapping an input from its original form to a more useful one.
The simplest kind of mapping to deal with is one-to-one (i.e., each different statement maps to a
single target representation that is different from that arising from any other statement).

(a) one-to-one mapping: consider the language of arithmetic, expressions in many programming
languages.
A:B+C*D

(b) many –to-one


In Many to one mappings free variantions are allowed .No two people speak identically. In fact, one
person does not always say a given word the same way. It shows a spectrogram produced by the
beginning of the utterance "Alpha gets alpha minus beta." A spectrogram shows how the sound energy is
distributed over the auditory frequency range as a function of time. In this example, the two different
patterns, each produced by the word "alpha." Even when we ignore the variability of the speech signal,
natural languages admit variability because of their richness.
Another example of many-to-one mappings, such as

Tell me all about thelast budget& result.-----------------

I like to see all reviews of budget and result.----------- (SEARCH KEYWORDS= BUDGET &
RESULT)

I am interested in budget & result------------------------

Many-to-one mappings require that the understanding system know about all the ways that a target
representation can be expressed in the source language.

(c ) one-to-many
It require a great deal of domain knowledge (in addition to the input itself) in order to make the
correct choice among the available target representations. An example of such a mapping (in which the
input can be said to be ambiguous) is the following sentence:

They are doing work -------------They are doing homework


------------They are doing office work
------------ They are doing household work
(d) Many –to many
there are many ways to say the same thing and a given statement may have many meanings.

3. Level of Interaction among Components


In most interesting understanding contexts, each input is composed of several components (lines, words,
symbols, or whatever). The mapping process is the simplest if each component can be mapped without
concern for the other components of the statement. Otherwise, as the number of interactions increases, so
does the complexity of the mapping.
Programming languages provide good examples of languages in which there is very little interaction
among the components of an input. For example, shows how changing one word of a statement requires
only a single change to one node of the corresponding parse tree.

:=

** +
COS

In image-understanding problems as well, a similar problem involving local indeterminacy arises.

4. Noise in Input

Understanding is the process of "interpreting an input and assigning it meaning. Unfortunately, in many
understanding situations the input to which meaning should be assigned is not always the input that is
presented to the understander. Because of the complex environment in which understanding usually
occurs, other things often interfere with the basic input before it reaches the understander. In perceptual
tasks, such as speech and image understanding, this problem is common. We rarely have the opportunity
to listen to each other against a background of silence. Thus we must take an input signal and separate the
speech component from the background noise component in order to understand the speech. The same
problem occurs in image understanding. If you look out of your car window in search of a particular store
sign, the image you will see i of the sign may be interfered with by many things, such as your windshield
wipers or the trees alongside the road. Although typed language is less susceptible to noise than is spoken
language, noise is still a problem. For example, typing errors are common, particularly if language is
being used interactively to communicate with a computer system.

UNDERSTANDING AS CONSTRAINT SATISFACTION

Many understanding tasks appear impossibly complex. The number of interpretations that can be
assigned to individual components of an input is large, and the number of combinations of those
components is enormous. But a closer analysis often reveals that many of the combinations cannot
actually occur. These natural constraints can be exploited in the understanding process to reduce the
complexity from unmanageable to tractable.

There are two important steps in the use of constraints in problem-solving:


1. Analyze the problem domain to determine what the constraints are.
2. Solve the problem by applying a constraint satisfaction algorithm that uses control strategy.

Look at one example of the use of this approach, the Waltz algorithm for line drawing.

Consider the drawing shown in Fig.3. Assume either that you have been given this drawing as the input or
that lower-level routines have already operated to extract these lines from an input photograph. The next
step in the analysis process is to determine the objects described by the lines.

We need first ,to identify each of the lines in the figure as representing either:
• An Obscuring Edge—A boundary between objects, or between objects and the background
• A Concave Edge—An edge between two faces that form an acute angle when viewed from outside
the object
• A Convex Edge—An edge between two faces that form an obtuse angle when viewed from outside
the object

Fig3: A Line Drawing

For more complex figures, other edge types, such as cracks between coplanar faces and shadow
edges between shadows and the background, would also be required. The approach we describe here
has, in fact, to handle these other edge types.

Determining the constraints

We are trying to solve is how to recognize individual objects in a figure. To do that, we have to first label all
the lines in the figure so that we know which ones correspond to boundaries between objects.

For boundary lines, we also need to indicate a direction, telling which side of the line corresponds to the
object and which to the background. This produces a set of four labels that can be attached to a given line. We
use the conventions shown in Fig.3 to show labellings.

+ Convex line

- Concave line

Boundary line with interior to the right(down)

Boundary line with interior to the right(up)

You might also like